The power of AI: on your visitors’ machine, at no extra cost.
Embed an assistant that runs entirely in the browser, on the visitor’s own GPU. No server, no per-token bill, no data leaving the device. You shape what it does with a single prompt.
Zero inference cost
The compute runs on your visitor’s GPU, not a server. No per-token bill, no rate limits, infinite scale. Flat price, unlimited usage.
Private by design
The data never leaves the browser. Nothing transits through us: a decisive argument for privacy-sensitive sites (health, legal, HR).
No server, no ops
No GPU fleet to run, no scaling to manage, no API keys to rotate. The model streams once from a CDN and is cached on the device.
Shaped by a prompt
You define what the AI does with a predefined instruction: its role, its logic, its guardrails. No fine-tuning, no data scientist required.
Try it: classify, extract & chat, on your GPU
An ultra-light model (LFM2.5 230M) classifies, extracts and chats: in French too. Shaped by a prompt, running entirely in your browser (no server). First run downloads it once (~149 MB), then it’s cached & offline.
How it works
Drop one <script> tag and write the instruction that shapes the assistant.
On first use, a lightweight model streams from a CDN and caches on the device (then it’s instant, even offline).
Every prompt runs on the visitor’s GPU through our WebGPU kernels: nothing is sent anywhere.
What it’s great at
A light on-device model shines on scoped tasks. The ones a good prompt fully defines:
Embed it on your site: Brimkern SDK
The SDK is live. One script tag mounts the assistant; a prompt and your knowledge base shape it. The model only downloads when a visitor opens the widget: your page score is untouched.
<script src="https://brimkern.com/sdk.js"></script>
<script>
Brimkern.embed({
title: "Store Assistant",
system: "You are the official store assistant. Help with sizing, shipping, and returns.",
knowledge: [
{ title: "Sizing Guide", text: "Sneakers fit true to size. Running shoes: order 0.5 size up. EU 42 = 27cm." },
{ title: "Returns", text: "100% free returns within 30 days. Refunds within 5 days." },
{ title: "Shipping", text: "Free shipping over $50 (2-4 days). Express 24h available." }
],
knowledgeBudget: 1200
});
</script>Try live demo with knowledge base Features: embeddable chat widget, headless sessions, custom system prompt, few-shot examples, local knowledge base (RAG: answers from YOUR content, selected locally, nothing sent anywhere), and local tools — arithmetic, today’s date, or your own functions, executed in your page and handed to the model as facts. embed() returns a handle — drive it, unmount it, subscribe to its events — the widget follows your page (light/dark/auto theme, corner, size, every label overridable), and every answer can name the notes it came from. Fully private and runs on the visitor’s GPU.
Our own engine, not a black box
Hand-written WebGPU kernels run the model; weights ship in our compact BRIK format, quantized down to int3 and streamed in seconds, then cached. A model is picked to fit: the loader even reads the visitor’s GPU and connection to recommend the right one.
Runs in modern browsers with WebGPU (Chrome, Edge, Safari, Firefox). Best for well-scoped tasks: not open-ended reasoning. First load downloads the model once; every visit after is instant and offline-capable.
Brimkern: local WebGPU inference. The embeddable SDK is live and free: the engine is open source (MIT).
Brimkern: open WebGPU engine, built by Romain Khanoyan. Local AI, WebGPU, on-device engines.